ulw-research
Team-first maximum-saturation research orchestration for omo-senpi. Scopes solo, ALWAYS asks which final format to render (PDF+DOCX default), then stands up a max-size cooperating team (team_create): one member per axis plus skeptic/red-team members for ultradebate/hyperdebate cross-critique, explore/librarian lanes, live ulw-loop journaling, an EXPAND loop until leads run dry, claims proven by code or the claim-graph gate, and a cited synthesis with charts/Mermaid/assets behind visual-QA and `writing` proofread gates. ACTIVATES ONLY on an explicit user demand for research: the word 'ulw-resea
Profile →npx skills add code-yeongyu/oh-my-openagent --skill ulw-research --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill activates only on an explicit user demand for research (various keywords and phrases including the word 'ulw-research'). It then coordinates a maximum-size research team, assigns one member per axis (distinct ownership), and adds a skeptic/red-team member for ultradebate cross-critique. It mandates exploring every relevant source, pursuing leads until exhausted, and producing a cited synthesis with charts, Mermaid visuals, assets, and a visual-QA and writing-proofread gates. It requires the final materials to match a pre-agreed final format and template, with an explicit Phase structure from scope to delivery and a closing briefing. It uses tools to create the team, send tasks, spawn exploration or librarian lanes, collect replies, track state, and eventually disband the team when done. It also enforces exhaustive coverage, debate rounds, code-backed verification, and an auditable session journal and claim graph.
How it works
- Activation: Wait for explicit demand using the phrases listed (e.g., 'ulw-research', '/ulw-research', '$ulw-research', or related debates or explicit research requests). On activation, output the line "ULW-RESEARCH MODE ENABLED!" and proceed.
- Team setup: Use team creation to stand up a crew with an inline_spec including a name and multiple members, each with a specific axis owner, category, and a prompt describing their axis scope. Include at least one skeptic (category 'ultrabrain') for cross-critique.
- Research workflow: Spawn exploration and librarian lanes and assign leads to task lanes via task_send, using a team_run_id to route work. Track state with task_create/task_list/task_update/task_get. Read finished lanes with task_output and end lanes with task_cancel. Disband with team_delete when complete.
- Documentation and artifacts: Maintain session journals, claim graphs, and annotated observation manifests, all forming a verifiable evidence trail for every claim, lead, and observation.
- Deliverable gates: Ensure the final materials have Phase 0 through Phase 4 validation, with alignment to the user’s requested final format and template, and provide a closing briefing detailing sources and run duration.
When to use it
Use only when the user explicitly demands exhaustive research, including phrases like 'ulw-research', 'ultradebate', or explicit requests for deep research or an ultra-precise investigation. Do not activate for ordinary questions, debugging, or general context gathering.
What it can touch
The skill relies on tools listed in the activation description: Claude Code, Codex, Cursor. It uses these tools to stand up teams, send tasks, spawn lanes, and track outputs. It requires and scripts through the team/task surfaces as described in the mapping.
Caveats
Activation is explicit and not automatic. The process is designed for exhaustive coverage and multi-person collaboration with red-team cross-critique and code-backed verification; it assumes access to the described tooling and license restrictions in the provided metadata. The license is NOASSERTION, and no guarantees of outcome are stated beyond the process and artifacts that must be produced.
# ULW-RESEARCH — Team-First Maximum-Saturation Research You are the research orchestrator AND the team lead. The user has explicitly ordered exhaustive research: scope the topic, stand up a cooperating team, fan out over every relevant source, chase every lead until the leads run dry, attack your own findings through debate, prove contested claims by running code, and deliver a synthesis in which every claim carries a citation or a proof. Exhaustive coverage is the assignment, not a risk to manage. ## Activation Run this skill only when the user explicitly demands it: the word "ulw-research" (also `/ulw-research`, `$ulw-research`), any "ulw" research wording, an "ultradebate" or "hyperdebate" research request, or an explicit request for research, deep research, or an ultra-precise investigation — in any language. An ordinary question, a debugging session, or another mode's context-gathering is not activation; answer those normally, and mention that `ulw-research` is available when a question would clearly benefit from it. Open your reply with the line `ULW-RESEARCH MODE ENABLED!`. If another active mode mandates its own first line (ultrawork does), print that mode's line first and
- Activation
- How this maps to omo-senpi
- Authority while active
- Success criteria
- Epistemic instrumentation
- Phase 0 — Scope solo, organize the brief
- Run it as a loop, and journal in real time
- Format-proposal gate — ALWAYS ask, before the team exists
- Phase 1 — Stand up the team (DEFAULT composition)
- Team lifecycle — one team, or a sequence, decided by scale and precision
- Member brief contract
- Phase 2 — Saturation wave
- Phase 3 — Expand and debate until convergence
- Excursions — dive deep on a new find, then surface back out
mkdir -p .omo/ulw-research/$(date +%Y%m%d-%H%M%S)
What does the ulw-research skill do?
Team-first maximum-saturation research orchestration for omo-senpi. Scopes solo, ALWAYS asks which final format to render (PDF+DOCX default), then stands up a max-size cooperating team (team_create): one member per axis plus skeptic/red-team members for ultradebate/hyperdebate cross-critique, explore/librarian lanes, live ulw-loop journaling, an EXPAND loop until leads run dry, claims proven by code or the claim-graph gate, and a cited synthesis with charts/Mermaid/assets behind visual-QA and `writing` proofread gates. ACTIVATES ONLY on an explicit user demand for research: the word 'ulw-resea
How do I install it?
Run `npx skills add code-yeongyu/oh-my-openagent --skill ulw-research --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From code-yeongyu/oh-my-openagent, a repository with 67,209 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.